In the BTech programme at LPU, you will study both machine learning and artificial intelligence (CSE). In your second year of CSE, you would study AI, and in your third year of BTech, you may minor in engineering in machine learning (ML) (CSE). Let me briefly describe each in this sentence.
ARTIFICIAL INTELLIGENCE: - The course introduces students to several approaches to artificial intelligence (AI) and covers a study of various knowledge representation strategies in AI applications. The notion of making machines intelligent will be implied by the course.
Students should be able to after taking this course to:
-
Explain the fundamental techniques used by artificial intelligence for problem-solving and learning.
-
Examine different search methods used to AI issues.
-
Use analytical principles and heuristic techniques to solve logical issues.
-
Investigate the many statistical reasoning methods to address AI issues.
-
justify the effectiveness of various gaming algorithms.
-
Talk about the ideas behind NLP, fuzzy logic, genetic algorithms, and machine learning.
MACHINE LEARNING:
COMPUTER VISION: This course covers a variety of computer vision-related subjects, including colour, light, picture generation, early, mid, and high-level vision. Also, the training covers topics like edge/corner/interest point recognition, local and global descriptors, and video tracking. Pupils will be able to finish computer vision assignments by using mathematical methods. Python and OpenCV will be used for practical experience.
DEEP LEARNING:
By assisting them in acquiring the knowledge and abilities to further their careers, the Deep Learning course offers students a route to make the most significant move in the field of AI. This course primarily focuses on the principles of deep learning, including generative adversarial networks, autoencoders, recurrent neural networks, and convolutional neural networks. TensorFlow and Keras will be used for practical training. Convolutional and recurrent neural networks may be implemented, along with deep learning to apply, and students will be able to construct and train deep neural networks.
FUNDAMENTALS OF MACHINE LEARNING:
This course focuses on the mathematical underpinnings of machine learning, such as how multivariate calculus optimises fitting functions to obtain good fits to data and how linear algebra relates to data. Python libraries will be used in-person to do feature engineering, data analysis, and visualisation so that machine learning models may be applied to the data. It also discusses several swarm intelligence algorithms that draw inspiration from genetic and ecological systems.
MACHINE LEARNING-I:
Students will design classifiers in this course that perform at the cutting edge on a range of problems, including as logistic regression, decision trees, boosting, and SVM. This is an interactive, hands-on course with plenty of examples and visualisations of how these methods will operate with actual data. Models should be evaluated using precision-recall metrics, and their hyperparameters should be adjusted. Moreover, numerous regression models for predicting continuous values will be covered.
MACHINE LEARNING-II
This course focuses on several clustering methods, including K-Means, hierarchical clustering, and density-based clustering. It also includes practical exercises using Python and datasets from the real world. The idea of reinforcement learning is also covered in this course, and the issues are formalised as Markov Decision Processes. To optimise decision-making processes, the value functions idea and their implementation will be carried out.
NATURAL LANGUAGE PROCESSING:
Using the use of Python and the Natural Language Tool Kit, this course teaches Natural Language Processing. Text categorization, language modelling, sequence tagging, word embeddings, etc. are the primary areas of attention. Students will gain real experience dealing with and evaluating material using a practical approach. The ability to create text-based issue solutions will be shown by students.